Medicine, Computers, and Linguistics

The increasingly complex informatics technology that evolved since 1950 created a new domain of knowledge and a new professional discipline. In this chapter we discuss the foundations and evolution of the fi eld of medical informatics, focusing on the role of publications, professional organizations, government, and industry in promoting the fi eld's growth, success, and impact. The earliest reports on biomedical applications of computers began to appear at conferences sponsored by professional engineering societies as early as 1947. The English term, medical informatics , was successfully introduced at an international meeting held in 1974. Subsequently the range of topics and the fi eld's scientifi c base have broadened, while academic informatics programs have been established at a growing number of institutions. The number of informatics articles published annually has grown rapidly, as have peer-reviewed informatics journals, the fi rst two of which were launched in the 1960s. The fi rst comprehensive medical informatics textbook (published in 1990) is now in its fourth edition. Starting in the 1960s, multiple organizations have been formed to focus on medical informatics; as their activities and infl uence increased, mergers followed, ultimately resulting in the creation of the American Medical Informatics Association (AMIA) in 1988. Other key players have included nursing, industry, academia, and the federal government, especially through the National Institutes of Health (NIH). More recently the fi eld has been further nurtured at the federal level by the Offi ce of the National Coordinator (ONC), which has championed the diffusion of electronic medical records, and the National Center for Advancing Translational Science (NCATS), which has funded clinical translational science awards and their supporting information systems.

Section: The Role Of Publicationsmentioning

confidence: 98%

Section: The Role Of Federal Agencies and Academiamentioning

confidence: 99%

The Creation of a New Discipline

Collen¹,

Shortliffe²

2015

“…Pratt [ 273 ] observed that the data a medical professional recorded and collected during the care of a patient was largely in a non-numeric form and in the United States was formulated almost exclusively in English language. He noted that a word, a phrase, or a sentence in this language was generally understood when spoken or read, and the marks of punctuation and the order of the presentation of words in a sentence represented quasi-formal structures that could be analyzed for content according to common rules for the recognition and validation of the string of language data that was a matter of morphology and syntax.…”

Section: Natural Language Process Ing ( Nlp )mentioning

confidence: 99%

Development of Medical Information Systems (MISs)

Collen¹,

Hammond

2015

By the late 1960s, mainframe-based hospital information systems (HISs) had been developed that could integrate patient data in a single database. In the 1970s, minicomputers made it possible to link the subsystem databases for clinical subspecialties and ancillary services to the mainframe and integrate patient data into the patient records stored there. In the 1980s, microcomputer-based systems that had evolved independently for specialized services became subsystems of larger medical information systems with an integrating central database management system. Storage grew cheaper; registries became databases; databases became data warehouses; and secondary clinical databases were developed. The recognition that databases were equally as important for querying and retrieving data as for documenting care lead to addressing issues of terminologies and other data standards. The fact that much data was unstructured led to the development of natural language processing (NLP) for retrieving and understanding unstructured data. In the 1990s, patient care data expanded in volume and complexity, and innovative clinical information systems offered hospitals and clinics new capabilities. From the 1990s on, the impact of the Internet and the Web grew, enabling global exchange of clinical data and medical knowledge. In the 2000s, distributed information systems allowed physicians using clinical workstations to enter orders and retrieve test results across multiple medical center databases. In the 2010s, federal support greatly increased the use of computer-based patient records. Global wireless communications with cloud storage for translational networks evolved that linked data warehouses in collaborating medical centers nationally and offered mobile e-health care for individual patients. Keywords

“…First published in 1965, SNOP coded medical terms into four major semantic categories: Topography (T) for the body site affected; Morphology (M) for the structural changes observed; Etiology (E) for the cause of the disease; and Function (F) for the abnormal changes in physiology [ 71 ]. Thus a patient with lung cancer who smoked cigarettes and had episodes of shortness of breath at night would be assigned the following string of SNOP terms: T2600 M8103 (bronchus, carcinoma); E6927 (tobacco-cigarettes); F7103 (paroxysmal nocturnal dyspnea) [ 55 ]. The use of SNOP was readily adopted by pathologists in the 1960s, as it was well suited for coding for computer entry when using punched cards.…”

Section: Encoding and Retrieval Of Anatomic Pathology Textmentioning

confidence: 99%

Anatomic Pathology Information Laboratory Information Systems and Natural Language Processing: Early History

Carter

Becich

Collen³

2015

Anatomic Pathology laboratories began to encode and retrieve diagnoses from paper reports using punched cards in the 1960s. When Anatomic Pathology Laboratory Information systems (APLIS) began to be used in the 1970s, pathology departments found that searching free text for diagnoses was hindered by the variability of terms for the same concept and by the amount of computer resources required. Consequently, system developers began to engineer natural language processing (NLP) algorithms to translate computationally ambiguous written language into coded concepts. At the same time, pathologists began to develop the Systemized Nomenclature of Pathologists (SNOP), which eventually developed into the internationally utilized ontology called the Systematized Nomenclature of Medicine Clinical Terms (SNOMED-CT). Systems in the 1970s used keywords based on concepts to encode reports and the development of query languages to retrieve them. By the 1980s, the user was guided through decision trees to the best matching concept code from data dictionaries that linked pathology systems with medical record systems, and linguistic analysis that converted natural language into a structured database. At that time, some advanced NLP systems had knowledge bases that indicated how experts would interpret the meaning of words in particular contexts, but most query languages were still based on the search and retrieval of encoded terms. Much has occurred since then, including the recognition of Pathology Informatics as a discipline and the use of many NLP algorithms as well as algorithms to scrub identifi ers from free text reports for research purposes.